In [24]:
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.cluster import KMeans
from sklearn import datasets
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
import random
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import sklearn.metrics as metrics
In [25]:
# 10대 매출비율,20대 매출비율 평균영업개월수 점포수 총 매출액
data=pd.read_csv("plus_living.csv")
data["total_living_people"]=data["total_living_people"] /1000
data["idx"]=np.arange(31547)
del data['Unnamed: 0']
del data['cm_code_name']
st_data=pd.DataFrame(data,columns=["10's_sales_rate","20's_sales_rate","30's_sales_rate","40's_sales_rate","50's_sales_rate","60's_sales_rate","simillar_store_number"])
# standardScaler 함수 사용하여 data 스케일링, 에러는 한글때문임, 한글 외에 모든 데이터 스케일링 됌
def standardScaler(header_list):
over_array = st_data[header_list]
a = pd.DataFrame(over_array)
a["idx"] = np.arange(31547)
train_data = a.values
standardScaler = StandardScaler()
print(standardScaler.fit(train_data))
train_data_standardScaled = standardScaler.transform(train_data)
st_df = pd.DataFrame(train_data_standardScaled, columns=['standard_over','B'])
del st_df['B']
st_data[header_list] = st_df
# columns들중에서 선별하여 스케일링 수행
header = list(data)
header
for a in header:
if(a == "10's_sales_rate" or a == "20's_sales_rate" or a == "30's_sales_rate" or a == "40's_sales_rate" or a == "50's_sales_rate" or a == "60's_sales_rate" or a == "simillar_store_number"):
standardScaler("{}".format(a))
#clustering
test_kmeans=pd.DataFrame(st_data,columns=["10's_sales_rate","20's_sales_rate","30's_sales_rate","40's_sales_rate","50's_sales_rate","60's_sales_rate","simillar_store_number"])
data_points=test_kmeans.values
kmeans=KMeans(n_clusters=5).fit(data_points)
test_kmeans['cluster_id']=kmeans.labels_
df = test_kmeans.copy()
test_kmeans["idx"] = np.arange(31547)
test_kmeans=pd.DataFrame(test_kmeans,columns=["cluster_id","idx"])
new=pd.merge(data,test_kmeans,on=["idx"])
del new["idx"]
test0 = rateof_1020_business_stnum0=new[new['cluster_id']==0]
test1 = rateof_1020_business_stnum1=new[new['cluster_id']==1]
test2 = rateof_1020_business_stnum2=new[new['cluster_id']==2]
test3 = rateof_1020_business_stnum3=new[new['cluster_id']==3]
test4 = rateof_1020_business_stnum4=new[new['cluster_id']==4]
In [26]:
Mean = pd.DataFrame({'test0' : test0.mean(), 'test1' : test1.mean(), 'test2' : test2.mean(), 'test3' : test3.mean(), 'test4' : test4.mean()})
Meandf = Mean.T
A = pd.DataFrame(Meandf , columns = ["act_jipyo_value", 'growth_jipyo_value', 'safety_jipyo_value'])
A = A.T
Mean
Out[26]:
In [27]:
A.plot(figsize=(12, 4), legend=True, fontsize=15)
Mean = pd.DataFrame({'test0' : test0.mean(), 'test1' : test1.mean(), 'test2' : test2.mean(), 'test3' : test3.mean(), 'test4' : test4.mean()})
Meandf = Mean.T
A2 = pd.DataFrame(Meandf , columns = ["10's_sales_rate", "20's_sales_rate", "30's_sales_rate","40's_sales_rate","50's_sales_rate","60's_sales_rate"])
A2 = A2.T
A2.plot(figsize=(12, 4), legend=True, fontsize=15)
Out[27]:
In [28]:
from matplotlib import font_manager, rc
font_name = font_manager.FontProperties(fname="c:/Windows/Fonts/malgun.ttf").get_name()
rc('font', family=font_name)
code_name = pd.read_csv("code_name.csv")
test0 = pd.merge(test0 , code_name, on="service_code")
test1 = pd.merge(test1 , code_name, on="service_code")
test2 = pd.merge(test2 , code_name, on="service_code")
test3 = pd.merge(test3 , code_name, on="service_code")
test4 = pd.merge(test4 , code_name, on="service_code")
plt.rcParams.update({'font.size': 40})
fig = plt.figure(figsize=(50,50))
ax1 = fig.add_subplot(321)
df0 = test0.service_code_name.value_counts()
df0=df0.head(5)
df0.plot.pie(autopct='%.2f%%')
plt.title("service_code")
plt.axis('equal')
ax2 = fig.add_subplot(322)
df1 = test1.service_code_name.value_counts()
df1=df1.head(5)
df1.plot.pie(autopct='%.2f%%')
plt.title("service_code")
plt.axis('equal')
ax3 = fig.add_subplot(323)
df2 = test2.service_code_name.value_counts()
df2=df2.head(5)
df2.plot.pie(autopct='%.2f%%')
plt.title("service_code")
plt.axis('equal')
ax4 = fig.add_subplot(324)
df3 = test3.service_code_name.value_counts()
df3=df3.head(5)
df3.plot.pie(autopct='%.2f%%')
plt.title("service_code")
plt.axis('equal')
ax5 = fig.add_subplot(325)
df4 = test4.service_code_name.value_counts()
df4=df4.head(5)
df4.plot.pie(autopct='%.2f%%')
plt.title("service_code")
plt.axis('equal')
plt.show()
In [29]:
import plotly.express as px
px.box(new,x="cluster_id",y="10's_sales_rate",color='cluster_id',notched=True)
In [30]:
px.box(new,x="cluster_id",y="20's_sales_rate",color='cluster_id',notched=True)
In [31]:
px.box(new,x="cluster_id",y="30's_sales_rate",color='cluster_id',notched=True)
In [32]:
px.box(new,x="cluster_id",y="40's_sales_rate",color='cluster_id',notched=True)
In [33]:
px.box(new,x="cluster_id",y="50's_sales_rate",color='cluster_id',notched=True)
In [34]:
px.box(new,x="cluster_id",y="60's_sales_rate",color='cluster_id',notched=True)
In [35]:
px.box(new,x="cluster_id",y="simillar_store_number",color='cluster_id',notched=True)
In [36]:
from sklearn.decomposition import PCA
plt.rcParams['axes.unicode_minus'] = False
pca = PCA(n_components=3)
X_scaled = st_data
pca.fit(X_scaled)
plt.rcParams.update({'font.size': 10})
# 처음 두 개의 주성분을 사용해 데이터를 변환합니다
X_pca = pca.transform(X_scaled)
X_pca = pd.DataFrame(X_pca)
print("원본 데이터 형태: {}".format(str(X_scaled.shape)))
print("축소된 데이터 형태: {}".format(str(X_pca.shape)))
clusterid=pd.DataFrame(new,columns=["cluster_id"])
X_pca['cluster_id'] = clusterid
fig = plt.figure(figsize = (15,15))
ax = fig.add_subplot( projection='3d')
x = X_pca[0]
y = X_pca[1]
z = X_pca[2]
ax.scatter(x,y,z, c=X_pca['cluster_id'], marker='o')
ax.set_xlabel('x axis')
ax.set_ylabel('y axis')
ax.set_zlabel('z axis')
plt.show()
In [4]:
import pandas_profiling as pp
pp.ProfileReport(test0)
Out[4]:
In [5]:
pp.ProfileReport(test1)
Out[5]:
In [6]:
pp.ProfileReport(test2)
Out[6]:
In [7]:
pp.ProfileReport(test3)
Out[7]:
In [8]:
pp.ProfileReport(test4)
Out[8]:
In [37]:
df.head()
Out[37]:
In [38]:
X_train, X_test = train_test_split(df, test_size=0.3, random_state=0)
y_train = X_train['cluster_id']
X_train = X_train.drop(['cluster_id'],axis=1)
y_test = X_test['cluster_id']
X_test = X_test.drop(['cluster_id'],axis =1)
X_train.shape, X_test.shape
Out[38]:
In [39]:
forest = RandomForestClassifier(n_estimators=600,max_depth = 12, random_state=42,criterion = 'entropy',max_features='auto')
forest.fit(X_train,y_train)
pred = forest.predict(X_test)
print("훈련 세트 정확도 : {:.3f}".format(forest.score(X_train,y_train)))
print("테스트 세트 정확도 : {:.3f}".format(forest.score(X_test,y_test)))
print("accuracy : ",accuracy_score(y_test,pred))
In [40]:
estimator = forest.estimators_[5]
from sklearn.tree import export_graphviz
# Export as dot file
export_graphviz(estimator, out_file='tree.dot',
feature_names = X_train.columns,
class_names = 'cluster_id',
rounded = True, proportion = False,
precision = 2, filled = True)
from IPython.display import Image
Image(filename = 'tree.jpeg')
Out[40]:
In [41]:
def plot_feature_importances_cancer(model):
n_features = X_train.shape[1]
plt.barh(range(n_features), model.feature_importances_, align='center')
plt.yticks(np.arange(n_features), X_train.columns)
plt.xlabel("attr importances")
plt.ylabel("attr")
plt.ylim(-1, n_features)
plt.rcParams.update({'font.size': 15})
plt.show()
plot_feature_importances_cancer(forest)
In [42]:
from mpl_toolkits.mplot3d import Axes3D
origin = X_test.copy()
origin['cluster_id'] = y_test
fig = plt.figure(figsize = (15,20))
###############################
ax = fig.add_subplot(321,projection = '3d')
ax.scatter(origin["20's_sales_rate"],
origin["30's_sales_rate"],
origin["40's_sales_rate"],c = origin['cluster_id'])
ax.set_xlabel("20's_sales_rate")
ax.set_ylabel("30's_sales_rate")
ax.set_zlabel("40's_sales_rate")
plt.title("original data of test data")
test = X_test.copy()
test['cluster_id'] = pred
ax = fig.add_subplot(322,projection = '3d')
ax.scatter(test["20's_sales_rate"],
test["30's_sales_rate"],
test["40's_sales_rate"],c = test['cluster_id'])
ax.set_xlabel("20's_sales_rate")
ax.set_ylabel("30's_sales_rate")
ax.set_zlabel("40's_sales_rate")
plt.title("predict data of test data")
##############################
ax = fig.add_subplot(323,projection = '3d')
ax.scatter(origin["50's_sales_rate"],
origin["60's_sales_rate"],
origin["simillar_store_number"],c = origin['cluster_id'])
ax.set_xlabel("50's_sales_rate")
ax.set_ylabel("60's_sales_rate")
ax.set_zlabel("simillar_store_number")
plt.title("original data of test data")
ax = fig.add_subplot(324,projection = '3d')
ax.scatter(test["50's_sales_rate"],
test["60's_sales_rate"],
test["simillar_store_number"],c = test['cluster_id'])
ax.set_xlabel("50's_sales_rate")
ax.set_ylabel("60's_sales_rate")
ax.set_zlabel("simillar_store_number")
plt.title("predict data of test data")
##############################
ax = fig.add_subplot(325,projection = '3d')
ax.scatter(origin["10's_sales_rate"],
origin["50's_sales_rate"],
origin["simillar_store_number"],c = origin['cluster_id'])
ax.set_xlabel("10's_sales_rate")
ax.set_ylabel("50's_sales_rate")
ax.set_zlabel("simillar_store_number")
plt.title("original data of test data")
ax = fig.add_subplot(326,projection = '3d')
ax.scatter(test["10's_sales_rate"],
test["50's_sales_rate"],
test["simillar_store_number"],c = test['cluster_id'])
ax.set_xlabel("10's_sales_rate")
ax.set_ylabel("50's_sales_rate")
ax.set_zlabel("simillar_store_number")
plt.title("predict data of test data")
plt.show()
In [43]:
import seaborn as sns
array = confusion_matrix(origin['cluster_id'], test['cluster_id'])
labels = ['0','1','2','3','4']
labels = np.asarray(labels)
sns.heatmap(array, annot=True, fmt='',cmap = 'BuPu')
from sklearn.metrics import classification_report
result = classification_report(origin['cluster_id'], test['cluster_id'], target_names=['class 0', 'class 1','class 2','class 3','class 4'])
print(result)
In [ ]: